Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to experiences and reflections on past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense verbs followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    recent past actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.73
     prochaines
    -0.67
     soon
    -0.62
     âgées
    -0.62
     segera
    -0.61
     domani
    -0.60
    Immediately
    -0.60
     للمعارف
    -0.58
     eventually
    -0.57
     AllAfrica
    -0.57
    POSITIVE LOGITS
     recientemente
    1.13
     recentemente
    1.07
     since
    1.07
     lately
    1.03
     sejak
    0.99
    recently
    0.98
     récemment
    0.98
     recent
    0.98
     recently
    0.98
    since
    0.97
    Act Density 0.233%

    No Known Activations